Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens that come before coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    and or ,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.71
    parsedMessage
    -0.69
    bootstrapcdn
    -0.69
    BeginInit
    -0.68
     Signalez
    -0.67
     للمعارف
    -0.67
     Chwiliwch
    -0.66
     surla
    -0.65
    رشف
    -0.63
     témoig
    -0.63
    POSITIVE LOGITS
     and
    0.39
     or
    0.36
     métro
    0.31
    ,
    0.28
     reclama
    0.28
    endpush
    0.28
     news
    0.27
     Cla
    0.27
    /
    0.26
     
    0.26
    Act Density 0.718%

    No Known Activations